i-2-7

Documents about i-2-7

• Stay Focused: Problem Drift in Multi-Agent Debate#128350arXiv (OAI)
• LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios#128396arXiv (OAI)
• Wildfire spread forecasting with Deep Learning#128397arXiv (OAI)
• MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering#131347arXiv (OAI)
• ANCHOR: LLM-driven Subject Conditioning for Text-to-Image Synthesis#173450arXiv (OAI Expanded)
• A Survey on Vision-Language-Action Models for Embodied AI#189141arXiv (OAI Expanded)
• OGX: An Open-Source, Vendor-Neutral Generative AI Application Server#609020arXiv (OAI Expanded)
• Calibrated Trust, Not Sharper Prediction: An Empirical Test of Uncertainty Fusion#609055arXiv (OAI Expanded)
• Evaluating Multimodal LLMs across Text and Audio Modalities for Accessible Disaster Assistance#609088arXiv (OAI Expanded)
• Interpretable Cross-Lingual Alignment in Small Language Models: Probing Cultural and Pragmatic Reasoning in Japanese-English Bilingual LLMs#609313arXiv (OAI Expanded)
• OGX: An Open-Source, Vendor-Neutral Generative AI Application Server#610082arXiv (All)
• Gathered, Not Admitted: How Attention Brings a Latent Variable into Verbalizable Form#610976arXiv (OAI Expanded)
• Gathered, Not Admitted: How Attention Brings a Latent Variable into Verbalizable Form#612453arXiv (All)
• Same Payload, Different Channel: Measuring Trust Asymmetry in Tool-Using Language Models#664285arXiv (OAI Expanded)
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems#664319arXiv (OAI Expanded)
• RSMeM: Knowledge-Enhanced Memory Evolution for Remote Sensing Agents with Systematic Evaluation#664381arXiv (OAI Expanded)
• TW-LegalBench: Measuring Taiwanese Legal Understanding#668576arXiv (OAI Expanded)
• What the "Spotless" Mind Remembers: How Knowledge Entanglement Shapes What Leaks After Unlearning in LLMs#674245arXiv (OAI Expanded)
• What the "Spotless" Mind Remembers: How Knowledge Entanglement Shapes What Leaks After Unlearning in LLMs#677442arXiv (All)
• MLLM-Routed Heterogeneous Ensembles for Robust Cross-Dataset Image Classification#677736arXiv (All)
• The Instability of Safety: How Random Seeds and Temperature Expose Inconsistent LLM Refusal Behavior#684310arXiv (All)
• Learned Relay Representations for Forward-Thinking Discrete Diffusion Models#684464arXiv (All)
• LV-ROVER-MLT: Low-Resource Maltese OCR by Synthetic Fine-Tuning and Multi-Stream Arbitration#684515arXiv (All)
• ProRetrieval: Learning to Orchestrate Hybrid Search via Executable Program Synthesis#780767arXiv (All)
• UIC-AIHealth4All at ArchEHR-QA 2026: Answer-First Evidence Grounding for Clinical Question Answering#780785arXiv (All)

Related topics